Query Categorization Based on Image Results

1. A computing system comprising: one or more processors; one or more non-transitory computer readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising: receiving a search query; determining, by processing the search query with a search engine, a plurality of images associated with a set of image results, wherein the set of image results are responsive to the search query; determining, by a ranking engine, a ranking of the set of image results based on the search query; processing the search query with a query classifier to determine a query classification, wherein the query classification is descriptive of one or more probabilities of the search query calling for images of one or more particular categories, wherein at least one of the one or more particular categories specifies a presence of a particular visual feature to be included in a search result, wherein the query classifier was trained to determine a probability that a query requests images associated with a respective category, wherein the query classifier was trained on a training dataset comprising: example queries and categorizations for each of the example queries; processing the set of image results with a categorizer engine to determine one or more particular image results of the set of image results are associated with the one or more particular categories; and increasing, via a rank modifier engine of the search engine, the ranking of the one or more particular image results based on the one or more particular image results having an association with the one or more particular categories of the search query.

2. The computing system of claim 1, wherein the training dataset further comprises: sets of feature vectors representing result images for the example queries.

3. The computing system of claim 1, wherein the operations further comprise: receiving a second query, wherein the second query comprises a second set of text characters; and determining the second query is associated with the search query.

4. The computing system of claim 3, wherein determining the second query is associated with the search query comprises: determining that the second query can be transformed into an alternative form that is same or similar to the search query.

5. The computing system of claim 4, wherein the operations further comprise: determining, by processing the second query with the search engine, a second set of image results; processing the second set of image results with the categorizer engine to determine one or more second particular image results of the second set of image results are associated with the one or more particular categories by: categorizing, by the categorizer engine, the one or more second particular image results of the second set of image results into the one or more particular categories associated with the search query; and modifying rankings of the second set of image results based on increasing rankings of the one or more second particular image results of the second set of image results based on the one or more particular categories.

6. The computing system of claim 1, wherein obtaining the plurality of images associated with the set of image results comprises determining an ordered list of documents based on the search query.

7. The computing system of claim 6, wherein the first set of image results comprise documents determined to have a high rank based on the first query.

8. The computing system of claim 6, wherein the ordered list of documents is based at least in part on click data associated with the first set of image results.

9. The computing system of claim 1, wherein the operations further comprise: decreasing, via the search engine, the ranking of one or more other image results based on the one or more particular categories of the search query.

10. The computing system of claim 1, wherein the operations further comprise: determining whether the one or more particular image results comprise a screenshot.

11. A computer-implemented method, the method comprising: receiving, by a computing system comprising one or more processors, a search query; determining, by the computing system and based on processing the search query with a search engine, a plurality of images associated with a set of image results, wherein the set of image results are responsive to the search query; determining, by a ranking engine, a ranking of the set of image results based on the search query; processing, by the computing system, the search query with a query classifier to determine a query classification, wherein the query classification is descriptive of one or more probabilities of the search query calling for images of one or more particular categories, wherein at least one of the one or more particular categories specifies a presence of a particular visual feature to be included in a search result, wherein the query classifier was trained to determine a probability that a query requests images associated with a respective category, wherein the query classifier was trained on a training dataset comprising: example queries and categorizations for each of the example queries; processing the set of image results with a categorizer engine to determine, by the computing system, one or more particular image results of the set of image results are associated with the one or more particular categories; and increasing, by the computing system and via the search engine, a ranking of the one or more particular image results based on the one or more particular image results having an association with the one or more particular categories of the first query.

12. The method of claim 11, wherein the one or more images of the plurality of images are selected based on a ranking of the set of image results, wherein the ranking is based on one or more past user selections.

13. The method of claim 11, wherein the one or more particular categories are associated with a number of faces depicted.

14. The method of claim 11, wherein processing, by the computing system, the search query with the query classifier to determine the query classification comprises: generating, by the computing system, a set of fingerprints associated with the set of image results; clustering, by the computing system and via an image cluster identifier, the set of image results into one or more clusters based on a measure of distance between respective fingerprints of the set of fingerprints associated with the set of image results; and determining, by the computing system, the query classification based on the one or more clusters.

15. The method of claim 14, wherein the query classification is descriptive of a specific topic, wherein the query classification is determined based on a number of clusters.

16. The method of claim 14, wherein processing, by the computing system, the search query with the query classifier to determine the query classification further comprises: associating, by the computing system, the search query with a canonical meaning based on the one or more clusters.

17. One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more computing devices comprising one or more processors, cause the one or more computing devices to perform operations, the operations comprising: receiving a search query via a user interface; determining, by processing the search query with a search engine associated with the user interface, a plurality of images associated with a set of image results, wherein the set of image results are responsive to the search query; determining, by a ranking engine, a ranking of the set of image results based on the search query; processing the search query with a query classifier to determine a query classification, wherein the query classification is descriptive of one or more probabilities of the search query calling for images of one or more particular categories, wherein at least one of the one or more particular categories specifies a presence of a particular visual feature to be included in a search result, wherein the query classifier was trained to determine a probability that a query requests images associated with a respective category, wherein the query classifier comprises a machine learning system that was trained on a training dataset comprising: example queries, a set of feature vectors representing result images for the example queries, and categorizations for each of the example queries; processing the set of image results with a categorizer engine to determine, via a result selector of the search engine, one or more particular image results of the set of image results are associated with the one or more particular categories; increasing, via a rank modifier engine of the search engine, a ranking of the one or more particular image results based on the one or more particular image results having an association with the one or more particular categories of the first query; and providing, via the user interface, a search results web page for display with a positioning of the one or more particular image results being determined based on the ranking.

18. The one or more non-transitory computer-readable media of claim 17, wherein determining the one or more particular image results of the set of image results are associated with the one or more particular categories comprises: determining how many faces are in each of the plurality of images.

19. The one or more non-transitory computer-readable media of claim 17, wherein the operations further comprise: determining a plurality of fingerprints for the plurality of images; and determining whether a subset of images of the plurality of images are similar based on the plurality of fingerprints.

20. The one or more non-transitory computer-readable media of claim 17, wherein the query classifier was generated via adaptive boosting, wherein invokes an image annotator for training.